wy-lee

Results 12 comments of wy-lee

Another simple solution you can try is using @insightface model. There they have a face_align under utils which uses ArcFace (together with SCRFD-10g) to align the facial features properly. However,...

I'd suggest sticking to MTCNN or TinaFace rather than using YOLOv5, accuracy in MTCNN is higher than YOLOv5

happened to me too, just download video C++ with dev set for C++ framework

Hi naifmeh, to fix the above code you can do this on the file ``` minicpmv.cpp ``` which is located under ```examples/minicpmv``` There what you can do is change the...

Hi Grigory, perhaps we can use LibriSpeech for measuring long audio (approx ~ 1000 hours but could trim it to fit for requirements). For short audio, we can use Libri-Light...

@foldl hi yes I'm looking at it, more or less likely to start after 12 as it's currently Chinese new year period...

Sorry please ignore the WER calculation above, I will develop another script since the calculations are completely off from what it should be . I will also look for a...

I have created a better and more robust lightweight script that meets the requirements @foldl , @ggerganov WER is measured at 0.3. It uses this lightweight dataset: https://arxiv.org/abs/2104.01497 and is...

The pull request contains the script as well as the full ~10mb dataset, making it fairly lightweight when measuring on the fly as well

I might be interested in this, have done some web dev before in other projects, what do you think if I were to try revamping the current website using JS...